A new screening tool for evaluation of steamflooding performance in Naturally Fractured Carbonate Reservoirs

Ali Shafiei, Maurice B. Dusseault, Sohrab Zendehboudi, Ioannis Chatzis

Research output: Contribution to journalArticle

52 Citations (Scopus)

Abstract

Appropriate production method selection for Viscous Oil (e.g., Heavy Oil, Extra Heavy Oil, and Bitumen) Naturally Fractured Carbonate Reservoirs (VO NFCRs) mostly depends on the quality of the fluid and reservoir properties. Selection of a particular production method for a reservoir is generally evaluated through an exhaustive experimental, field pilot, and mathematical modeling approach. In the absence of robust and quick predictive tools, using connectionist techniques for performance prediction of a particular production method can be a valuable asset. In this study, a new screening tool is developed based on Artificial Neural Networks (ANNs) optimized with Particle Swarm Optimization (PSO) to assess the performance of steamflooding in VO NFCRs. As expected, Recovery Factor (RF) and Cumulative Steam to Oil Ratio (CSOR) during steamflooding are highly affected by the magnitudes of oil saturation and viscosity. The developed PSO-ANN model, conventional ANN and statistical correlations were examined using real data. Comparison of the predictions and real data implies the superiority of the proposed PSO-ANN model with an absolute average error percentage < 6.5%, a determination coefficient (R2) > 0.98, and Mean Squared Error (MSE) < 0.06, in contrast with conventional ANN model and empirical correlations for prediction of RF and CSOR. This indicates a great potential for application of hybrid PSO-ANN models to screen Viscous Oil carbonate reservoirs for steamflooding.

Original languageEnglish
Pages (from-to)502-514
Number of pages13
JournalFuel
Volume108
DOIs
Publication statusPublished - Jan 1 2013
Externally publishedYes

Fingerprint

Carbonates
Screening
Neural networks
Particle swarm optimization (PSO)
Oils
asphalt
Steam
Crude oil
Recovery
Petroleum reservoirs
Viscosity
Fluids

Keywords

  • Artificial neural network
  • Naturally fractured carbonates
  • Screening tool
  • Steamflooding performance
  • Viscous oil

ASJC Scopus subject areas

  • Chemical Engineering(all)
  • Fuel Technology
  • Energy Engineering and Power Technology
  • Organic Chemistry

Cite this

A new screening tool for evaluation of steamflooding performance in Naturally Fractured Carbonate Reservoirs. / Shafiei, Ali; Dusseault, Maurice B.; Zendehboudi, Sohrab; Chatzis, Ioannis.

In: Fuel, Vol. 108, 01.01.2013, p. 502-514.

Research output: Contribution to journalArticle

Shafiei, Ali ; Dusseault, Maurice B. ; Zendehboudi, Sohrab ; Chatzis, Ioannis. / A new screening tool for evaluation of steamflooding performance in Naturally Fractured Carbonate Reservoirs. In: Fuel. 2013 ; Vol. 108. pp. 502-514.
@article{a972d66e70b54002bcbca3a9f7614a6d,
title = "A new screening tool for evaluation of steamflooding performance in Naturally Fractured Carbonate Reservoirs",
abstract = "Appropriate production method selection for Viscous Oil (e.g., Heavy Oil, Extra Heavy Oil, and Bitumen) Naturally Fractured Carbonate Reservoirs (VO NFCRs) mostly depends on the quality of the fluid and reservoir properties. Selection of a particular production method for a reservoir is generally evaluated through an exhaustive experimental, field pilot, and mathematical modeling approach. In the absence of robust and quick predictive tools, using connectionist techniques for performance prediction of a particular production method can be a valuable asset. In this study, a new screening tool is developed based on Artificial Neural Networks (ANNs) optimized with Particle Swarm Optimization (PSO) to assess the performance of steamflooding in VO NFCRs. As expected, Recovery Factor (RF) and Cumulative Steam to Oil Ratio (CSOR) during steamflooding are highly affected by the magnitudes of oil saturation and viscosity. The developed PSO-ANN model, conventional ANN and statistical correlations were examined using real data. Comparison of the predictions and real data implies the superiority of the proposed PSO-ANN model with an absolute average error percentage < 6.5{\%}, a determination coefficient (R2) > 0.98, and Mean Squared Error (MSE) < 0.06, in contrast with conventional ANN model and empirical correlations for prediction of RF and CSOR. This indicates a great potential for application of hybrid PSO-ANN models to screen Viscous Oil carbonate reservoirs for steamflooding.",
keywords = "Artificial neural network, Naturally fractured carbonates, Screening tool, Steamflooding performance, Viscous oil",
author = "Ali Shafiei and Dusseault, {Maurice B.} and Sohrab Zendehboudi and Ioannis Chatzis",
year = "2013",
month = "1",
day = "1",
doi = "10.1016/j.fuel.2013.01.056",
language = "English",
volume = "108",
pages = "502--514",
journal = "Fuel",
issn = "0016-2361",
publisher = "Elsevier",

}

TY - JOUR

T1 - A new screening tool for evaluation of steamflooding performance in Naturally Fractured Carbonate Reservoirs

AU - Shafiei, Ali

AU - Dusseault, Maurice B.

AU - Zendehboudi, Sohrab

AU - Chatzis, Ioannis

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Appropriate production method selection for Viscous Oil (e.g., Heavy Oil, Extra Heavy Oil, and Bitumen) Naturally Fractured Carbonate Reservoirs (VO NFCRs) mostly depends on the quality of the fluid and reservoir properties. Selection of a particular production method for a reservoir is generally evaluated through an exhaustive experimental, field pilot, and mathematical modeling approach. In the absence of robust and quick predictive tools, using connectionist techniques for performance prediction of a particular production method can be a valuable asset. In this study, a new screening tool is developed based on Artificial Neural Networks (ANNs) optimized with Particle Swarm Optimization (PSO) to assess the performance of steamflooding in VO NFCRs. As expected, Recovery Factor (RF) and Cumulative Steam to Oil Ratio (CSOR) during steamflooding are highly affected by the magnitudes of oil saturation and viscosity. The developed PSO-ANN model, conventional ANN and statistical correlations were examined using real data. Comparison of the predictions and real data implies the superiority of the proposed PSO-ANN model with an absolute average error percentage < 6.5%, a determination coefficient (R2) > 0.98, and Mean Squared Error (MSE) < 0.06, in contrast with conventional ANN model and empirical correlations for prediction of RF and CSOR. This indicates a great potential for application of hybrid PSO-ANN models to screen Viscous Oil carbonate reservoirs for steamflooding.

AB - Appropriate production method selection for Viscous Oil (e.g., Heavy Oil, Extra Heavy Oil, and Bitumen) Naturally Fractured Carbonate Reservoirs (VO NFCRs) mostly depends on the quality of the fluid and reservoir properties. Selection of a particular production method for a reservoir is generally evaluated through an exhaustive experimental, field pilot, and mathematical modeling approach. In the absence of robust and quick predictive tools, using connectionist techniques for performance prediction of a particular production method can be a valuable asset. In this study, a new screening tool is developed based on Artificial Neural Networks (ANNs) optimized with Particle Swarm Optimization (PSO) to assess the performance of steamflooding in VO NFCRs. As expected, Recovery Factor (RF) and Cumulative Steam to Oil Ratio (CSOR) during steamflooding are highly affected by the magnitudes of oil saturation and viscosity. The developed PSO-ANN model, conventional ANN and statistical correlations were examined using real data. Comparison of the predictions and real data implies the superiority of the proposed PSO-ANN model with an absolute average error percentage < 6.5%, a determination coefficient (R2) > 0.98, and Mean Squared Error (MSE) < 0.06, in contrast with conventional ANN model and empirical correlations for prediction of RF and CSOR. This indicates a great potential for application of hybrid PSO-ANN models to screen Viscous Oil carbonate reservoirs for steamflooding.

KW - Artificial neural network

KW - Naturally fractured carbonates

KW - Screening tool

KW - Steamflooding performance

KW - Viscous oil

UR - http://www.scopus.com/inward/record.url?scp=84883599515&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883599515&partnerID=8YFLogxK

U2 - 10.1016/j.fuel.2013.01.056

DO - 10.1016/j.fuel.2013.01.056

M3 - Article

AN - SCOPUS:84883599515

VL - 108

SP - 502

EP - 514

JO - Fuel

JF - Fuel

SN - 0016-2361

ER -